© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5885
    Prev
    Next
    INDEX
    Explanations

    references to the element silver or items associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NgModule
    -0.94
    Vidite
    -0.83
     فريبيس
    -0.83
    }{*}{
    -0.83
    makeText
    -0.81
    帖最后由
    -0.81
    PMailer
    -0.80
     Mahomet
    -0.78
     שוליים
    -0.77
    owels
    -0.77
    POSITIVE LOGITS
     Silver
    3.02
     silver
    3.02
    Silver
    2.97
     SILVER
    2.71
    silver
    2.69
    SILVER
    2.39
     Silverman
    1.96
     Silvers
    1.85
     silvery
    1.82
     zilver
    1.80
    Activations Density 0.076%

    No Known Activations